Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Citations in scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Weekend
    -0.08
     STAT
    -0.08
     kể
    -0.07
    ╙
    -0.07
    ackbar
    -0.07
    萆
    -0.07
     seçenek
    -0.07
    召
    -0.06
    _YELLOW
    -0.06
    legend
    -0.06
    POSITIVE LOGITS
    斛
    0.08
     clubhouse
    0.07
    &quot
    0.07
     greatly
    0.07
    母親
    0.07
    🦑
    0.07
     worlds
    0.07
     Sexual
    0.07
    _certificate
    0.07
    סרט
    0.06
    Act Density 0.003%

    No Known Activations